An active learning workflow for predicting misfit volume in body-centered cubic refractory high-entropy alloys
Shunshun Liu, Prasanna V Balachandran · 2026
Read An active learning workflow for predicting misfit volume in body-centered cubic refractory high-entropy alloys by Shunshun Liu, Prasanna V Balachandran (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13500629.txt.
Description
Shunshun Liu and Prasanna V Balachandran build in 2026 an active learning workflow that predicts a key strength descriptor in refractory high-entropy alloys, exotic mixes of several heat-resistant metals in equal shares. The descriptor, misfit volume, captures how much each atom's size and electronic character distorts the crystal, and crude averaging rules miss the local relaxation that matters. Their loop couples quantum-level calculations with ensemble machine learning across 126 five-element alloys, choosing which compositions to calculate next for maximum information gain.
Analysis plots showed atomic size mismatch driving the descriptor directly, while differences in electronegativity, the pull atoms exert on electrons, partly compensated electronically. Feeding the learned values into a mechanistic strength model reproduced measured yield strengths well across diverse compositions in the reported checks. The workflow promises cheaper screening of alloys for jet engines, nuclear systems, and power plants.
Catalog record
| CREATOR | Shunshun Liu, Prasanna V Balachandran |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 39635 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |